Advances in Differential Privacy and Differentially Private Machine Learning

• URL: http://arxiv.org/abs/2404.04706v1
• Date: Sat, 6 Apr 2024 18:49:24 GMT
• Title: Advances in Differential Privacy and Differentially Private Machine Learning
• Authors: Saswat Das, Subhankar Mishra,
• Abstract summary: differential privacy in particular contexts like data publishing, specific machine learning tasks, analysis of unstructured data, location privacy, etc. Recent developments in the theory of differential privacy along with newer DP variants, viz. Renyi DP and Concentrated DP, novel mechanisms and techniques, and the theoretical developments in differentially private machine learning in proper detail. In addition, this survey discusses its applications to privacy-preserving machine learning in practice and a few practical implementations of DP.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: There has been an explosion of research on differential privacy (DP) and its various applications in recent years, ranging from novel variants and accounting techniques in differential privacy to the thriving field of differentially private machine learning (DPML) to newer implementations in practice, like those by various companies and organisations such as census bureaus. Most recent surveys focus on the applications of differential privacy in particular contexts like data publishing, specific machine learning tasks, analysis of unstructured data, location privacy, etc. This work thus seeks to fill the gap for a survey that primarily discusses recent developments in the theory of differential privacy along with newer DP variants, viz. Renyi DP and Concentrated DP, novel mechanisms and techniques, and the theoretical developments in differentially private machine learning in proper detail. In addition, this survey discusses its applications to privacy-preserving machine learning in practice and a few practical implementations of DP.

Related papers

• A Decade of Metric Differential Privacy: Advancements and Applications [8.865292595200964]
  Metric Differential Privacy (mDP) builds upon the core principles of Differential Privacy (DP) by incorporating various distance metrics. mDP offers privacy guarantees for a wide range of applications, such as location-based services, text analysis, and image processing. This paper provides a comprehensive survey of mDP research from 2013 to 2024, tracing its development from the foundations of DP.
  arXiv  Detail & Related papers  (2025-02-13T05:18:24Z)
• Differentially Private Random Feature Model [52.468511541184895]
  We produce a differentially private random feature model for privacy-preserving kernel machines. We show that our method preserves privacy and derive a generalization error bound for the method.
  arXiv  Detail & Related papers  (2024-12-06T05:31:08Z)
• Differential Privacy Overview and Fundamental Techniques [63.0409690498569]
  This chapter is meant to be part of the book "Differential Privacy in Artificial Intelligence: From Theory to Practice" It starts by illustrating various attempts to protect data privacy, emphasizing where and why they failed. It then defines the key actors, tasks, and scopes that make up the domain of privacy-preserving data analysis.
  arXiv  Detail & Related papers  (2024-11-07T13:52:11Z)
• Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey [1.89915151018241]
  Differential Privacy has become a widely popular method for data protection in machine learning. This survey provides an overview of the state-of-the-art of differentially private centralized deep learning.
  arXiv  Detail & Related papers  (2023-09-28T12:44:59Z)
• A Unified View of Differentially Private Deep Generative Modeling [60.72161965018005]
  Data with privacy concerns comes with stringent regulations that frequently prohibited data access and data sharing. Overcoming these obstacles is key for technological progress in many real-world application scenarios that involve privacy sensitive data. Differentially private (DP) data publishing provides a compelling solution, where only a sanitized form of the data is publicly released.
  arXiv  Detail & Related papers  (2023-09-27T14:38:16Z)
• On the Importance of Architecture and Feature Selection in Differentially Private Machine Learning [2.387686431425822]
  We study a pitfall in the typical workflow for differentially private machine learning. The use of differentially private learning algorithms in a "drop-in" fashion yields overly complex and poorly performing models.
  arXiv  Detail & Related papers  (2022-05-13T15:57:34Z)
• Debugging Differential Privacy: A Case Study for Privacy Auditing [60.87570714269048]
  We show that auditing can also be used to find flaws in (purportedly) differentially private schemes. In this case study, we audit a recent open source implementation of a differentially private deep learning algorithm and find, with 99.99999999% confidence, that the implementation does not satisfy the claimed differential privacy guarantee.
  arXiv  Detail & Related papers  (2022-02-24T17:31:08Z)
• Statistical Privacy Guarantees of Machine Learning Preprocessing Techniques [1.198727138090351]
  We adapt a privacy violation detection framework based on statistical methods to measure privacy levels of machine learning pipelines. We apply the newly created framework to show that resampling techniques used when dealing with imbalanced datasets cause the resultant model to leak more privacy.
  arXiv  Detail & Related papers  (2021-09-06T14:08:47Z)
• Sensitivity analysis in differentially private machine learning using hybrid automatic differentiation [54.88777449903538]
  We introduce a novel textithybrid automatic differentiation (AD) system for sensitivity analysis. This enables modelling the sensitivity of arbitrary differentiable function compositions, such as the training of neural networks on private data. Our approach can enable the principled reasoning about privacy loss in the setting of data processing.
  arXiv  Detail & Related papers  (2021-07-09T07:19:23Z)
• Applications of Differential Privacy in Social Network Analysis: A Survey [60.696428840516724]
  Differential privacy is effective in sharing information and preserving privacy with a strong guarantee. Social network analysis has been extensively adopted in many applications, opening a new arena for the application of differential privacy.
  arXiv  Detail & Related papers  (2020-10-06T19:06:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.